Raman Group: AI-Enhanced ECG and Digital Twin Modelling for Early Diagnosis and Mechanistic Stratification in Cardiomyopathies

About the Research 

Hypertrophic cardiomyopathy (HCM) and Dilated Cardiomyopathy (DCM) can be genetically mediated heart muscle disease characterised by abnormal muscle thickness, inefficient energy utilization (in HCM & DCM), microstructural changes (e.g., disarray in HCM), and microvascular dysfunction. These structural and metabolic abnormalities lead to arrhythmias, sudden death, and heart failure, but early diagnosis and accurate risk stratification remain challenging. This translational project aims to combine artificial intelligence (AI) analysis of the 12-lead ECG with computational heart modelling ("digital twin") to better understand and predict disease progression in inherited cardiomyopathies.

There are two projects:

1. AI for ECG-based Early Diagnosis and Risk Stratification: Develop and train machine learning models (e.g. convolutional neural networks) on digital ECGs from large HCM registries (e.g. HCMR, other multicentre and local  cohorts), predict outcomes such as arrhythmia, progression to obstruction, or heart failure, identify subtle ECG patterns linked to subclinical hypertrophy, disarray, or fibrosis, benchmark AI predictions against cardiac MRI phenotypes and genotype status

2. Digital Twin and Computational Modelling for Mechanistic Insights: Generate patient-specific digital heart models using imaging (e.g. CMR-derived wall thickness, strain, perfusion) and ECG data, simulate the electrical and mechanical consequences of structural abnormalities, examine how these alterations give rise to arrhythmic risk and abnormal conduction and study the impact of novel treatments.

The integration of AI and computational physiology will help develop a biophysically-informed ECG risk model, guiding therapy and screening in genetically predisposed.

This project is ideally suited to students with a background in biomedical sciences, engineering, computer science, or data science, with an interest in translational cardiovascular research. Prior experience with Python, MATLAB, or R will be essential. Enthusiasm for working at the interface of cardiology, medical imaging, and machine learning is welcomed. Interested candidates are encouraged to reach out to PI Betty.raman@cardiov.ox.ac.uk with a copy of their CV to discuss project details.

This MSc by Research project may be suitable for part-time research.

Training Opportunities

1. Digital ECG signal analysis – Work with raw waveform data for feature extraction and AI model training under supervision of experts in Computer Science Department.
2. Machine learning for clinical applications – Apply deep learning (CNNs, transformers) to ECG time series
3. Cardiac computational modelling – Build and run patient-specific electromechanical models of the heart
4. Integration of imaging and ECG – Learn to correlate ECG features with CMR markers (e.g. fibrosis, perfusion, strain)
5. Digital twin development – Use tools like Chaste, OpenEP, or CARPentry to build digital heart models
6. Inverse modelling and parameter fitting – Infer hidden pathophysiology (e.g. disarray) from ECG + imaging
7. Clinical cardiology exposure – Interpret ECGs and imaging from patients with HCM and related disorders
8. Multi-modal risk prediction modelling – Combine ECG, imaging, and genotype data for survival analysis
9. Model validation and explainability – Perform SHAP/LIME analysis to interpret AI decisions
10. Translational collaboration – Work across cardiology, biomedical engineering, AI, and genetics

Students are encouraged to attend the MRC Weatherall Institute of Molecular Medicine Graduate Course, which takes place in the autumn of their first year. Running over several days, this course helps students to develop basic research and presentation skills, as well as introducing them to a wide range of scientific techniques and principles, ensuring that students have the opportunity to build a broad-based understanding of differing research methodologies.

Generic skills training is offered through the Medical Sciences Division's Skills Training Programme. This programme offers a comprehensive range of courses covering many important areas of researcher development: knowledge and intellectual abilities, personal effectiveness, research governance and organisation, and engagement, influence, and impact. Students are actively encouraged to take advantage of the training opportunities available to them.

As well as the specific training detailed above, students will have access to a wide range of seminars and training opportunities through the many research institutes and centres based in Oxford.

The Department has a successful mentoring scheme, open to graduate students, which provides an additional possible channel for personal and professional development outside the regular supervisory framework. We hold an Athena SWAN Silver Award in recognition of our efforts to build a happy and rewarding environment where all staff and students are supported to achieve their full potential.

Additional Supervisors

1. Alfonso Bueno 

2. Blanca Rodriguez

3. Vincente Grau & Rina Ariga 

Publications